Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

1 files changed, 59 insertions, 3 deletions

diff --git a/include/net/dsa.h b/include/net/dsa.h
index e1a2610a0e06..33f40c1ec379 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -50,6 +50,7 @@ struct phylink_link_state;
 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE	20
 #define DSA_TAG_PROTO_SEVILLE_VALUE		21
 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE		22
+#define DSA_TAG_PROTO_SJA1110_VALUE		23
 
 enum dsa_tag_protocol {
 	DSA_TAG_PROTO_NONE		= DSA_TAG_PROTO_NONE_VALUE,
@@ -75,6 +76,7 @@ enum dsa_tag_protocol {
 	DSA_TAG_PROTO_XRS700X		= DSA_TAG_PROTO_XRS700X_VALUE,
 	DSA_TAG_PROTO_OCELOT_8021Q	= DSA_TAG_PROTO_OCELOT_8021Q_VALUE,
 	DSA_TAG_PROTO_SEVILLE		= DSA_TAG_PROTO_SEVILLE_VALUE,
+	DSA_TAG_PROTO_SJA1110		= DSA_TAG_PROTO_SJA1110_VALUE,
 };
 
 struct packet_type;
@@ -91,7 +93,8 @@ struct dsa_device_ops {
 	 * as regular on the master net device.
 	 */
 	bool (*filter)(const struct sk_buff *skb, struct net_device *dev);
-	unsigned int overhead;
+	unsigned int needed_headroom;
+	unsigned int needed_tailroom;
 	const char *name;
 	enum dsa_tag_protocol proto;
 	/* Some tagging protocols either mangle or shift the destination MAC
@@ -100,7 +103,6 @@ struct dsa_device_ops {
 	 * its RX filter.
 	 */
 	bool promisc_on_master;
-	bool tail_tag;
 };
 
 /* This structure defines the control interfaces that are overlayed by the
@@ -283,6 +285,12 @@ struct dsa_port {
 	 */
 	const struct dsa_netdevice_ops *netdev_ops;
 
+	/* List of MAC addresses that must be forwarded on this port.
+	 * These are only valid on CPU ports and DSA links.
+	 */
+	struct list_head	fdbs;
+	struct list_head	mdbs;
+
 	bool setup;
 };
 
@@ -297,6 +305,13 @@ struct dsa_link {
 	struct list_head list;
 };
 
+struct dsa_mac_addr {
+	unsigned char addr[ETH_ALEN];
+	u16 vid;
+	refcount_t refcount;
+	struct list_head list;
+};
+
 struct dsa_switch {
 	bool setup;
 
@@ -407,6 +422,21 @@ static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p)
 	return NULL;
 }
 
+static inline bool dsa_port_is_dsa(struct dsa_port *port)
+{
+	return port->type == DSA_PORT_TYPE_DSA;
+}
+
+static inline bool dsa_port_is_cpu(struct dsa_port *port)
+{
+	return port->type == DSA_PORT_TYPE_CPU;
+}
+
+static inline bool dsa_port_is_user(struct dsa_port *dp)
+{
+	return dp->type == DSA_PORT_TYPE_USER;
+}
+
 static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p)
 {
 	return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED;
@@ -474,6 +504,32 @@ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port)
 	return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index);
 }
 
+/* Return true if this is the local port used to reach the CPU port */
+static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port)
+{
+	if (dsa_is_unused_port(ds, port))
+		return false;
+
+	return port == dsa_upstream_port(ds, port);
+}
+
+/* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning
+ * that the routing port from @downstream_ds to @upstream_ds is also the port
+ * which @downstream_ds uses to reach its dedicated CPU.
+ */
+static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds,
+					     struct dsa_switch *downstream_ds)
+{
+	int routing_port;
+
+	if (upstream_ds == downstream_ds)
+		return true;
+
+	routing_port = dsa_routing_port(downstream_ds, upstream_ds->index);
+
+	return dsa_is_upstream_port(downstream_ds, routing_port);
+}
+
 static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp)
 {
 	const struct dsa_switch *ds = dp->ds;
@@ -926,7 +982,7 @@ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb,
 {
 #if IS_ENABLED(CONFIG_NET_DSA)
 	const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops;
-	int tag_len = ops->overhead;
+	int tag_len = ops->needed_headroom;
 
 	*offset = tag_len;
 	*proto = ((__be16 *)skb->data)[(tag_len / 2) - 1];